Technical Diagnostics of Industrial Robots Using Vibration Signals: Case Study on Detecting Base Unfastening

In the domain of modern manufacturing digitalization, artificial intelligence tools are increasingly employed for condition monitoring and technical diagnostics. However, the majority of existing methodologies primarily concentrate on the technical diagnosis of rotating machines, with a noticeable lack of research addressing these issues in sequential machines. In this paper, we deal with the selection of suitable vibration signal characteristics for the detection of an industrial robot's release from its base during a handling operation. Statistical methods, including one-way ANOVA and t-tests, were used to identify the most significant features, which allowed us to isolate vibration metrics with significant predictive potential. These selected features were then used as inputs to various machine learning models to evaluate the hypothesis that these parameters can reliably indicate fastening releasing events. The results show that the optimized parameters significantly improve the detection accuracy, thus providing a reliable basis for future applications in predictive maintenance and monitoring. The findings represent an advance in robotic condition monitoring, providing a structured approach to feature selection that improves the reliability of disconnection detection in automated systems with potential applicability in various industrial environments.